{"total":56,"rows":[{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2203.11852","title":"Representation Bias in Data: A Survey on Identification and Resolution Techniques","created":"2022-03-22","cited_by_count":37,"area":null},{"id":"2410.07991","title":"Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targets","created":"2024-10-10","cited_by_count":31,"area":null},{"id":"2312.06861","title":"Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates","created":"2023-12-11","cited_by_count":26,"area":null},{"id":"2401.16727","title":"Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models","created":"2024-01-30","cited_by_count":26,"area":null},{"id":"2410.02657","title":"Hate Personified: Investigating the role of LLMs in content moderation","created":"2024-10-03","cited_by_count":25,"area":null},{"id":"2404.01651","title":"NLP Systems That Can't Tell Use from Mention Censor Counterspeech, but Teaching the Distinction Helps","created":"2024-04-02","cited_by_count":20,"area":null},{"id":"2311.09585","title":"LifeTox: Unveiling Implicit Toxicity in Life Advice","created":"2023-11-16","cited_by_count":14,"area":null},{"id":"2406.07353","title":"Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities","created":"2024-06-11","cited_by_count":13,"area":null},{"id":"2503.01623","title":"Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2303.03387","title":"CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network","created":"2023-03-02","cited_by_count":12,"area":null},{"id":"2405.17034","title":"FUGNN: Harmonizing Fairness and Utility in Graph Neural Networks","created":"2024-05-27","cited_by_count":11,"area":null},{"id":"2406.03953","title":"Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2403.04085","title":"Don't Blame the Data, Blame the Model: Understanding Noise and Bias When Learning from Subjective Annotations","created":"2024-03-06","cited_by_count":10,"area":null},{"id":"2410.03448","title":"\"Cold, Calculated, and Condescending\": How AI Identifies and Explains Ableism Compared to Disabled People","created":"2024-10-04","cited_by_count":10,"area":null},{"id":"2505.24341","title":"Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings","created":"2025-05-30","cited_by_count":10,"area":null},{"id":"2302.07371","title":"BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models","created":"2023-02-14","cited_by_count":8,"area":null},{"id":"2406.00046","title":"Hate Speech Detection with Generalizable Target-aware Fairness","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2307.02763","title":"Your spouse needs professional help: Determining the Contextual Appropriateness of Messages through Modeling Social Relationships","created":"2023-07-06","cited_by_count":6,"area":null},{"id":"2308.10592","title":"BAN-PL: a Novel Polish Dataset of Banned Harmful and Offensive Content from Wykop.pl web service","created":"2023-08-21","cited_by_count":6,"area":null},{"id":"2505.15773","title":"ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2311.04345","title":"A Taxonomy of Rater Disagreements: Surveying Challenges & Opportunities from the Perspective of Annotating Online Toxicity","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2407.05977","title":"Exploring Human-LLM Conversations: Mental Models and the Originator of Toxicity","created":"2024-07-08","cited_by_count":4,"area":null},{"id":"2209.05294","title":"A Review of Challenges in Machine Learning based Automated Hate Speech Detection","created":"2022-09-12","cited_by_count":3,"area":null},{"id":"2406.14099","title":"Let Guidelines Guide You: A Prescriptive Guideline-Centered Data Annotation Methodology","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2406.14154","title":"Watching the Watchers: A Comparative Fairness Audit of Cloud-based Content Moderation Services","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2407.03551","title":"Leveraging Machine Learning to Identify Gendered Stereotypes and Body Image Concerns on Diet and Fitness Online Forums","created":"2024-07-04","cited_by_count":3,"area":null},{"id":"2504.10359","title":"DICE: A Framework for Dimensional and Contextual Evaluation of Language Models","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2509.25539","title":"Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2307.10213","title":"Mitigating Bias in Conversations: A Hate Speech Classifier and Debiaser with Prompts","created":"2023-07-14","cited_by_count":2,"area":null},{"id":"2309.11896","title":"Focal Inferential Infusion Coupled with Tractable Density Discrimination for Implicit Hate Detection","created":"2023-09-21","cited_by_count":2,"area":null},{"id":"2401.09244","title":"Cross-lingual Offensive Language Detection: A Systematic Review of Datasets, Transfer Approaches and Challenges","created":"2024-01-17","cited_by_count":2,"area":null},{"id":"2405.09543","title":"Algorithmic Fairness: A Tolerance Perspective","created":"2024-04-26","cited_by_count":2,"area":null},{"id":"2411.08135","title":"On the Role of Speech Data in Reducing Toxicity Detection Bias","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2412.04942","title":"A Federated Approach to Few-Shot Hate Speech Detection for Marginalized Communities","created":"2024-12-06","cited_by_count":2,"area":null},{"id":"2505.11958","title":"Counterspeech the ultimate shield! Multi-Conditioned Counterspeech Generation through Attributed Prefix Learning","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2510.05291","title":"Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2601.09250","title":"When to Invoke: Refining LLM Fairness with Toxicity Assessment","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2310.02357","title":"On the definition of toxicity in NLP","created":"2023-10-03","cited_by_count":1,"area":null},{"id":"2403.08115","title":"Legally Binding but Unfair? Towards Assessing Fairness of Privacy Policies","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2403.19340","title":"Dataverse: Open-Source ETL (Extract, Transform, Load) Pipeline for Large Language Models","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2601.08668","title":"Analyzing Bias in False Refusal Behavior of Large Language Models for Hate Speech Detoxification","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2604.25580","title":"Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2410.13313","title":"Mitigating Biases to Embrace Diversity: A Comprehensive Annotation Benchmark for Toxic Language","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2503.16072","title":"Toxicity Is a Property of Communicative Events: A Contextual Stress Measurement Framework for NLP","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2504.13085","title":"Tackling Social Bias against the Poor: A Dataset and Taxonomy on Aporophobia","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2505.17642","title":"A Survey on Stereotype Detection in Natural Language Processing","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.14567","title":"Controlling Context: Generative AI at Work in Integrated Circuit Design and Other High-Precision Domains","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2509.14264","title":"Defining, Understanding, and Detecting Online Toxicity: Challenges and Machine Learning Approaches","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2603.14843","title":"ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.09094","title":"Few-Shot Contrastive Adaptation for Audio Abuse Detection in Low-Resource Indic Languages","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.15984","title":"Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.02493","title":"Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthropomorphism, and Maxims","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.23175","title":"Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2608.12361","title":"New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2610.01005","title":"Tolerance-Based Fairness Auditing: Violation Certification and Sensitivity Screening","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}